Corrigendum: Retrieving rice (Oryza sativa L.) net photosynthetic rate from UAV multispectral images based on machine learning methods.

[This corrects the article DOI: 10.3389/fpls.2022.1088499.].

Retrieving rice (Oryza sativa L.) net photosynthetic rate from UAV multispectral images based on machine learning methods.

Photosynthesis is the key physiological activity in the process of crop growth and plays an irreplaceable role in carbon assimilation and yield formation. This study extracted rice (Oryza sativa L.) canopy reflectance based on the UAV multispectral images and analyzed the correlation between 25 vegetation indices (VIs), three textural indices (TIs), and net photosynthetic rate (Pn) at different growth stages. Linear regression (LR), support vector regression (SVR), gradient boosting decision tree (GBDT), random forest (RF), and multilayer perceptron neural network (MLP) models were employed for Pn estimation, and the modeling accuracy was compared under the input condition of VIs, VIs combined with TIs, and fusion of VIs and TIs with plant height (PH) and SPAD. The results showed that VIs and TIs generally had the relatively best correlation with Pn at the jointing-booting stage and the number of VIs with significant correlation (p< 0.05) was the largest. Therefore, the employed models could achieve the highest overall accuracy [coefficient of determination (R 2) of 0.383-0.938]. However, as the growth stage progressed, the correlation gradually weakened and resulted in accuracy decrease (R 2 of 0.258-0.928 and 0.125-0.863 at the heading-flowering and ripening stages, respectively). Among the tested models, GBDT and RF models could attain the best performance based on only VIs input (with R 2 ranging from 0.863 to 0.938 and from 0.815 to 0.872, respectively). Furthermore, the fusion input of VIs, TIs with PH, and SPAD could more effectively improve the model accuracy (R 2 increased by 0.049-0.249, 0.063-0.470, and 0.113-0.471, respectively, for three growth stages) compared with the input combination of VIs and TIs (R 2 increased by 0.015-0.090, 0.001-0.139, and 0.023-0.114). Therefore, the GBDT and RF model with fused input could be highly recommended for rice Pn estimation and the methods could also provide reference for Pn monitoring and further yield prediction at field scale.

Predicted infiltration for sodic/saline soils from reclaimed coastal areas: sensitivity to model parameters.

This study was conducted to assess the influences of soil surface conditions and initial soil water content on water movement in unsaturated sodic soils of reclaimed coastal areas. Data was collected from column experiments in which two soils from a Chinese coastal area reclaimed in 2007 (Soil A, saline) and 1960 (Soil B, nonsaline) were used, with bulk densities of 1.4 or 1.5 g/cm(3). A 1D-infiltration model was created using a finite difference method and its sensitivity to hydraulic related parameters was tested. The model well simulated the measured data. The results revealed that soil compaction notably affected the water retention of both soils. Model simulations showed that increasing the ponded water depth had little effect on the infiltration process, since the increases in cumulative infiltration and wetting front advancement rate were small. However, the wetting front advancement rate increased and the cumulative infiltration decreased to a greater extent when θ0 was increased. Soil physical quality was described better by the S parameter than by the saturated hydraulic conductivity since the latter was also affected by the physical chemical effects on clay swelling occurring in the presence of different levels of electrolytes in the soil solutions of the two soils.

Growth and comprehensive quality index of tomato under rain shelters in response to different irrigation and drainage treatments.

The effects of two levels of irrigation water (100%, 60%) and buried underground pipe depths (0.8 m, 0.6 m) under rain shelters' conditions on yield and some quality parameters of tomato were investigated. A fully randomized factorial experiment was conducted between April and August in 2011 and 2012 at Hohai University. It was found that drainage treatments enhanced biomass production, whereas soil desiccation led to biomass reduction. At 60 cm buried underground pipe depths, the drought treatments increased the mean root weight and root-shoot ratio by 14% and 39%, respectively. The main effects of drainage treatments on the fruit quality were increases in total soluble solids (TSS), soluble sugar (SS), and vitamin C (VC) compared to the control. In addition, drainage treatments increased the average yield by 13% and 9%, respectively, in both years. The drought treatments did not significantly alter fruit yield, although mean single fruit weight was slightly reduced. Instead, these treatments tend to have great potential to improve fruit quality (TSS, SS, and VC) to variable extents. In both years, the drought treatment at 60 cm buried underground pipe depths proved to possess the highest comprehensive quality index based on Principal Component Analysis.